Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of comment symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    math `tr`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGenerated
    -0.63
    ftagPool
    -0.60
    әрмәләр
    -0.60
     autorytatywna
    -0.60
     betweenstory
    -0.59
     resourceCulture
    -0.57
    invokeLater
    -0.55
     незавершена
    -0.54
     '{@
    -0.54
    NameInMap
    -0.52
    POSITIVE LOGITS
    smith
    0.38
    Törté
    0.37
    here
    0.35
     Here
    0.34
     here
    0.34
     sprink
    0.33
    Here
    0.33
    //
    0.32
    buttonBar
    0.32
    isma
    0.32
    Act Density 0.001%

    No Known Activations